List your company

Code Generation on MBPP (Acc, NFE)

42.6AccuracySWD
16.623.3530.136.85Apr 18, 2026

Evaluation results

MethodLinks
SWDBackbone=Dream-7B, Scoring Metric=Entropy, Decoding Strategy=Stability-Weighted Decoding, lambda=52026.0442.6109.4
SWDBackbone=LLaDA-8B, Scoring Metric=Confidence, Decoding Strategy=Stability-Weighted Decoding, lambda=52026.0434.866.8
SWDBackbone=LLaDA-8B, Scoring Metric=Margin, Decoding Strategy=Stability-Weighted Decoding, lambda=52026.043465.9
BaseBackbone=Dream-7B, Scoring Metric=Entropy, Decoding Strategy=Vanilla EB Sampler2026.0433.2174.7
BaseBackbone=Dream-7B, Scoring Metric=Confidence, Decoding Strategy=Vanilla EB Sampler2026.0429.4212.4
SWDBackbone=LLaDA-8B, Scoring Metric=Entropy, Decoding Strategy=Stability-Weighted Decoding, lambda=52026.0426.6108
SWDBackbone=Dream-7B, Scoring Metric=Confidence, Decoding Strategy=Stability-Weighted Decoding, lambda=52026.0426.286.2
BaseBackbone=LLaDA-8B, Scoring Metric=Margin, Decoding Strategy=Vanilla EB Sampler2026.0426108.3
BaseBackbone=LLaDA-8B, Scoring Metric=Confidence, Decoding Strategy=Vanilla EB Sampler2026.0423.4110.3
BaseBackbone=Dream-7B, Scoring Metric=Margin, Decoding Strategy=Vanilla EB Sampler2026.0423.4202.6
BaseBackbone=LLaDA-8B, Scoring Metric=Entropy, Decoding Strategy=Vanilla EB Sampler2026.0418.4114.1
SWDBackbone=Dream-7B, Scoring Metric=Margin, Decoding Strategy=Stability-Weighted Decoding, lambda=52026.0417.669.9